Wavelets2D#

class zrad.filtering.wavelet.Wavelets2D(wavelet_type, padding_type, response_map, decomposition_level, rotation_invariance=False)[source]#

2D separable wavelet filtering evaluated slice-wise.

Each response map combines low-pass (L) and high-pass (H) wavelet kernels along the two in-plane axes. The result keeps the original image grid and is intended for downstream radiomics feature extraction.

Parameters:

  • wavelet_type ({"db3", "db2", "coif1", "haar"}) – Wavelet family used to obtain low- and high-pass filter kernels.

  • padding_type ({"constant", "nearest", "wrap", "reflect"}) – Boundary handling mode used during convolution.

  • response_map ({"LL", "HL", "LH", "HH"}) – Low/high-pass kernel combination for the two in-plane axes.

  • decomposition_level ({1, 2}) – Wavelet decomposition level.

  • rotation_invariance (bool, optional) – If true, average responses over four in-plane rotations.

Methods

apply(image)

Apply the filter to an image or set RoiData.filtered_image.

get_params()

Return filter parameters mapped to their configured values.
Wavelets2D.apply(image)#

Apply the filter to an image or set RoiData.filtered_image.

Parameters:

image (Image or RoiData) – Input image to filter. If RoiData is supplied, filtering is applied to image.image and the result is stored as filtered_image in the returned ROI data. Existing intensity, texture, and IVH prepared fields are cleared.

Returns:

filtered – Filtered image, or ROI data with filtered_image updated.

Return type:

Image or RoiData

Wavelets2D.get_params()#

Return filter parameters mapped to their configured values.

Returns:

params – Constructor parameters stored by the filter instance.

Return type:

dict